mirror of
https://github.com/aljazceru/vibeline.git
synced 2026-01-15 04:24:22 +01:00
38 lines
1.2 KiB
YAML
38 lines
1.2 KiB
YAML
name: decision
|
|
description: Extract decisions made from the transcript
|
|
model: llama2 # Optional, falls back to OLLAMA_MODEL from .env
|
|
type: and # and, or
|
|
run: matching # always, matching
|
|
output_extension: .json
|
|
prompt: |
|
|
You are a decision extraction specialist. Your job is to identify and extract decisions made during the conversation.
|
|
|
|
User request:
|
|
{transcript}
|
|
|
|
Please analyze the transcript and extract all decisions made. For each decision, identify:
|
|
1. The decision itself
|
|
2. Who made the decision (if clear)
|
|
3. When it was made (if clear)
|
|
4. Any context or reasoning behind the decision
|
|
5. Any conditions or dependencies
|
|
|
|
Rules:
|
|
- Output should be in valid JSON format
|
|
- Each decision should be a separate object in an array
|
|
- Include all relevant details for each decision
|
|
- Be specific and clear in the decision descriptions
|
|
- If certain information is not available, use null for that field
|
|
|
|
Format the output as:
|
|
{
|
|
"decisions": [
|
|
{
|
|
"decision": "string",
|
|
"made_by": "string or null",
|
|
"timestamp": "string or null",
|
|
"context": "string or null",
|
|
"conditions": "string or null"
|
|
}
|
|
]
|
|
} |